feat(data-access): expand PageIntent model to track attempts

packages/spacecat-shared-data-access/src/models/page-intent/index.d.ts

@@ -18,11 +18,19 @@ export interface PageIntent extends BaseModel {
     getUrl(): string;
     getPageIntent(): string;
     getTopic(): string;
+    getAnalysisStatus(): string | null;
+    getAnalysisAttempts(): number | null;
+    getLastAnalysisAt(): string | null;
+    getAnalysisError(): { code: string; message: string; details?: any } | null;
 
     setSiteId(siteId: string): PageIntent;
     setUrl(url: string): PageIntent;
     setPageIntent(pageIntent: string): PageIntent;
     setTopic(topic: string): PageIntent;
+    setAnalysisStatus(status: string): PageIntent;
+    setAnalysisAttempts(attempts: number): PageIntent;
+    setLastAnalysisAt(timestamp: string): PageIntent;
+    setAnalysisError(error: { code: string; message: string; details?: any }): PageIntent;
 }
 
 export interface PageIntentCollection extends BaseCollection<PageIntent> {

packages/spacecat-shared-data-access/src/models/page-intent/page-intent.model.js

@@ -28,6 +28,11 @@ class PageIntent extends BaseModel {
     COMMERCIAL: 'COMMERCIAL',
   };
 
+  static ANALYSIS_STATUS = {
+    SUCCESS: 'SUCCESS',
+    FAILED: 'FAILED',
+  };
+
   // add any custom methods or overrides here
 }
 

packages/spacecat-shared-data-access/src/models/page-intent/page-intent.schema.js

@@ -10,7 +10,9 @@
  * governing permissions and limitations under the License.
  */
 
-import { isValidUrl } from '@adobe/spacecat-shared-utils';
+import {
+  isValidUrl, isObject, isInteger, isIsoDate,
+} from '@adobe/spacecat-shared-utils';
 
 import SchemaBuilder from '../base/schema.builder.js';
 import PageIntent from './page-intent.model.js';
@@ -51,6 +53,33 @@ const schema = new SchemaBuilder(PageIntent, PageIntentCollection)
     default: PageIntent.DEFAULT_UPDATED_BY,
   })
 
+  // analysis tracking fields
+  .addAttribute('analysisStatus', {
+    type: Object.values(PageIntent.ANALYSIS_STATUS),
+    required: false,
+  })
+  .addAttribute('analysisAttempts', {
+    type: 'number',
+    required: false,
+    default: 0,
+    validate: (value) => !value || isInteger(value),
+  })
+  .addAttribute('lastAnalysisAt', {
+    type: 'string',
+    required: false,
+    validate: (value) => !value || isIsoDate(value),
+  })
+  .addAttribute('analysisError', {
+    type: 'map',
+    required: false,
+    properties: {
+      code: { type: 'string' },
+      message: { type: 'string' },
+      details: { type: 'any' },
+    },
+    validate: (value) => !value || (isObject(value) && value.code && value.message),
+  })
+
   // allow fetching the single record by its URL
   .addIndex(
     { composite: ['url'] },

packages/spacecat-shared-data-access/test/fixtures/page-intents.fixture.js

@@ -17,13 +17,27 @@ const pageIntents = [
     url: 'https://example0.com/page0',
     pageIntent: 'INFORMATIONAL',
     topic: 'firefly',
+    analysisStatus: 'SUCCESS',
+    analysisAttempts: 1,
+    lastAnalysisAt: '2025-11-07T10:00:00.000Z',
   },
   {
     pageIntentId: 'e61a9beb-d3ec-4d53-8652-1b6b43127b3e',
     siteId: '78fec9c7-2141-4600-b7b1-ea5c78752b91',
     url: 'https://example1.com/page1',
     pageIntent: 'NAVIGATIONAL',
     topic: 'photoshop',
+    analysisStatus: 'FAILED',
+    analysisAttempts: 3,
+    lastAnalysisAt: '2025-11-07T11:30:00.000Z',
+    analysisError: {
+      code: 'INVALID_RESPONSE',
+      message: 'AI model returned invalid page intent format',
+      details: {
+        rawResponse: 'UNKNOWN_INTENT',
+        attemptedAt: '2025-11-07T11:30:00.000Z',
+      },
+    },
   },
   {
     pageIntentId: '36fc2fe4-6fd4-45dd-8cf3-2f1aedf778e3',

packages/spacecat-shared-data-access/test/it/page-intent/page-intent.test.js

@@ -107,4 +107,76 @@ describe('PageIntent IT', async () => {
     expect(pi.getTopic()).to.equal(updates.topic);
     expect(pi.getUpdatedBy()).to.equal(updates.updatedBy);
   });
+
+  it('creates a page intent with successful analysis tracking', async () => {
+    const data = {
+      url: 'https://www.example.com/success-page',
+      siteId: '1c86ba81-f3cc-48d8-8b06-1f9ac958e72d',
+      pageIntent: 'COMMERCIAL',
+      topic: 'success-topic',
+      analysisStatus: 'SUCCESS',
+      analysisAttempts: 1,
+      lastAnalysisAt: '2025-11-07T12:00:00.000Z',
+    };
+    const pi = await PageIntent.create(data);
+
+    checkPageIntent(pi);
+
+    expect(pi.getAnalysisStatus()).to.equal('SUCCESS');
+    expect(pi.getAnalysisAttempts()).to.equal(1);
+    expect(pi.getLastAnalysisAt()).to.equal('2025-11-07T12:00:00.000Z');
+    expect(pi.getAnalysisError()).to.be.undefined;
+  });
+
+  it('creates a page intent with failed analysis tracking', async () => {
+    const data = {
+      url: 'https://www.example.com/failed-page',
+      siteId: '1c86ba81-f3cc-48d8-8b06-1f9ac958e72d',
+      pageIntent: 'INFORMATIONAL',
+      topic: 'failed-topic',
+      analysisStatus: 'FAILED',
+      analysisAttempts: 3,
+      lastAnalysisAt: '2025-11-07T13:00:00.000Z',
+      analysisError: {
+        code: 'TIMEOUT',
+        message: 'Analysis timed out after 30 seconds',
+        details: {
+          attemptedAt: '2025-11-07T13:00:00.000Z',
+          timeoutMs: 30000,
+        },
+      },
+    };
+    const pi = await PageIntent.create(data);
+
+    checkPageIntent(pi);
+
+    expect(pi.getAnalysisStatus()).to.equal('FAILED');
+    expect(pi.getAnalysisAttempts()).to.equal(3);
+    expect(pi.getLastAnalysisAt()).to.equal('2025-11-07T13:00:00.000Z');
+    expect(pi.getAnalysisError()).to.deep.equal(data.analysisError);
+  });
+
+  it('updates analysis tracking fields', async () => {
+    const sample = sampleData.pageIntents[2];
+    const pi = await PageIntent.findByUrl(sample.getUrl());
+
+    pi.setAnalysisStatus('FAILED');
+    pi.setAnalysisAttempts(2);
+    pi.setLastAnalysisAt('2025-11-07T14:00:00.000Z');
+    pi.setAnalysisError({
+      code: 'INVALID_FORMAT',
+      message: 'Response format was invalid',
+      details: { rawResponse: 'bad data' },
+    });
+
+    await pi.save();
+
+    expect(pi.getAnalysisStatus()).to.equal('FAILED');
+    expect(pi.getAnalysisAttempts()).to.equal(2);
+    expect(pi.getLastAnalysisAt()).to.equal('2025-11-07T14:00:00.000Z');
+    expect(pi.getAnalysisError()).to.deep.include({
+      code: 'INVALID_FORMAT',
+      message: 'Response format was invalid',
+    });
+  });
 });

packages/spacecat-shared-html-analyzer/xunit.xml

@@ -0,0 +1,10 @@
+<testsuite name="Mocha Tests" tests="8" failures="0" errors="0" skipped="0" timestamp="Fri, 07 Nov 2025 09:29:20 GMT" time="0.096">
+<testcase classname="HTML Visibility Analyzer analyzeTextComparison" name="should analyze content differences" file="/Users/cwisse/Projects/spacecat-shared/packages/spacecat-shared-html-analyzer/test/index.test.js" time="0.086"/>
+<testcase classname="HTML Visibility Analyzer analyzeTextComparison" name="should handle identical content" file="/Users/cwisse/Projects/spacecat-shared/packages/spacecat-shared-html-analyzer/test/index.test.js" time="0.001"/>
+<testcase classname="HTML Visibility Analyzer analyzeTextComparison" name="should handle empty content" file="/Users/cwisse/Projects/spacecat-shared/packages/spacecat-shared-html-analyzer/test/index.test.js" time="0.001"/>
+<testcase classname="HTML Visibility Analyzer calculateStats" name="should provide basic comparison statistics" file="/Users/cwisse/Projects/spacecat-shared/packages/spacecat-shared-html-analyzer/test/index.test.js" time="0.001"/>
+<testcase classname="HTML Visibility Analyzer calculateBothScenarioStats" name="should provide statistics for both scenarios" file="/Users/cwisse/Projects/spacecat-shared/packages/spacecat-shared-html-analyzer/test/index.test.js" time="0.002"/>
+<testcase classname="HTML Visibility Analyzer stripTagsToText" name="should extract text content from HTML" file="/Users/cwisse/Projects/spacecat-shared/packages/spacecat-shared-html-analyzer/test/index.test.js" time="0.001"/>
+<testcase classname="HTML Visibility Analyzer stripTagsToText" name="should remove navigation elements when ignoreNavFooter is true" file="/Users/cwisse/Projects/spacecat-shared/packages/spacecat-shared-html-analyzer/test/index.test.js" time="0.001"/>
+<testcase classname="HTML Visibility Analyzer stripTagsToText" name="should keep navigation elements when ignoreNavFooter is false" file="/Users/cwisse/Projects/spacecat-shared/packages/spacecat-shared-html-analyzer/test/index.test.js" time="0.001"/>
+</testsuite>